Image analysis

Count and extract image objects

Upload one image to detect and count separate objects, preview them, and receive metadata plus extracted object images.

Image

Object counter and extractor

Live

Image

Preview mode

Sensitivity

Minimum size

Merge nearby

Exclude text

Padding

Max objects

Preview

Count

Metadata

{
  "count": 17,
  "image": {
    "width": 1024,
    "height": 576
  },
  "objects": [
    {
      "id": 1,
      "bbox": {
        "x": 58,
        "y": 6,
        "width": 239,
        "height": 254
      },
      "padded_bbox": {
        "x": 58,
        "y": 6,
        "width": 239,
        "height": 254
      },
      "area_percent": 5.21
    },
    {
      "id": 2,
      "bbox": {
        "x": 360,
        "y": 11,
        "width": 81,
        "height": 84
      },
      "padded_bbox": {
        "x": 360,
        "y": 11,
        "width": 81,
        "height": 84
      },
      "area_percent": 0.73
    },
    {
      "id": 3,
      "bbox": {
        "x": 460,
        "y": 15,
        "width": 162,
        "height": 227
      },
      "padded_bbox": {
        "x": 460,
        "y": 15,
        "width": 162,
        "height": 227
      },
      "area_percent": 3.84
    },
    {
      "id": 4,
      "bbox": {
        "x": 653,
        "y": 15,
        "width": 164,
        "height": 133
      },
      "padded_bbox": {
        "x": 653,
        "y": 15,
        "width": 164,
        "height": 133
      },
      "area_percent": 1.7
    },
    {
      "id": 5,
      "bbox": {
        "x": 876,
        "y": 21,
        "width": 122,
        "height": 146
      },
      "padded_bbox": {
        "x": 876,
        "y": 21,
        "width": 122,
        "height": 146
      },
      "area_percent": 2.28
    },
    {
      "id": 6,
      "bbox": {
        "x": 298,
        "y": 75,
        "width": 154,
        "height": 186
      },
      "padded_bbox": {
        "x": 298,
        "y": 75,
        "width": 154,
        "height": 186
      },
      "area_percent": 1.35
    },
    {
      "id": 7,
      "bbox": {
        "x": 726,
        "y": 162,
        "width": 209,
        "height": 90
      },
      "padded_bbox": {
        "x": 726,
        "y": 162,
        "width": 209,
        "height": 90
      },
      "area_percent": 2.02
    },
    {
      "id": 8,
      "bbox": {
        "x": 26,
        "y": 194,
        "width": 183,
        "height": 142
      },
      "padded_bbox": {
        "x": 26,
        "y": 194,
        "width": 183,
        "height": 142
      },
      "area_percent": 1.9
    },
    {
      "id": 9,
      "bbox": {
        "x": 366,
        "y": 228,
        "width": 358,
        "height": 142
      },
      "padded_bbox": {
        "x": 366,
        "y": 228,
        "width": 358,
        "height": 142
      },
      "area_percent": 4.14
    },
    {
      "id": 10,
      "bbox": {
        "x": 874,
        "y": 243,
        "width": 131,
        "height": 172
      },
      "padded_bbox": {
        "x": 874,
        "y": 243,
        "width": 131,
        "height": 172
      },
      "area_percent": 2.5
    },
    {
      "id": 11,
      "bbox": {
        "x": 16,
        "y": 317,
        "width": 153,
        "height": 147
      },
      "padded_bbox": {
        "x": 16,
        "y": 317,
        "width": 153,
        "height": 147
      },
      "area_percent": 1.82
    },
    {
      "id": 12,
      "bbox": {
        "x": 236,
        "y": 296,
        "width": 177,
        "height": 256
      },
      "padded_bbox": {
        "x": 236,
        "y": 296,
        "width": 177,
        "height": 256
      },
      "area_percent": 4.4
    },
    {
      "id": 13,
      "bbox": {
        "x": 669,
        "y": 341,
        "width": 218,
        "height": 214
      },
      "padded_bbox": {
        "x": 669,
        "y": 341,
        "width": 218,
        "height": 214
      },
      "area_percent": 5.84
    },
    {
      "id": 14,
      "bbox": {
        "x": 443,
        "y": 373,
        "width": 100,
        "height": 131
      },
      "padded_bbox": {
        "x": 443,
        "y": 373,
        "width": 100,
        "height": 131
      },
      "area_percent": 1.37
    },
    {
      "id": 15,
      "bbox": {
        "x": 110,
        "y": 450,
        "width": 124,
        "height": 113
      },
      "padded_bbox": {
        "x": 110,
        "y": 450,
        "width": 124,
        "height": 113
      },
      "area_percent": 1.3
    },
    {
      "id": 16,
      "bbox": {
        "x": 896,
        "y": 437,
        "width": 101,
        "height": 125
      },
      "padded_bbox": {
        "x": 896,
        "y": 437,
        "width": 101,
        "height": 125
      },
      "area_percent": 1.17
    },
    {
      "id": 17,
      "bbox": {
        "x": 550,
        "y": 482,
        "width": 100,
        "height": 83
      },
      "padded_bbox": {
        "x": 550,
        "y": 482,
        "width": 100,
        "height": 83
      },
      "area_percent": 0.87
    }
  ]
}

Extracted

Open in Fuser

Runs in your browser. Your files are never uploaded.

How tools work

A tool is a small app you describe in plain words. Try this one here, then keep it on your Fuser canvas and connect it to the rest of your work.

A tool on the Fuser canvas with its controls and result

1. Try it here

Add your own file or text and adjust the controls. Live tools run in your browser, so nothing is uploaded.

Two tools chained together on the Fuser canvas

2. Open it in Fuser

Sign up free and the tool opens on your canvas with this example wired in, ready to connect to images, video or text from other nodes.

A Tool node with a description of the tool to build

3. Describe your own

Need something different? Describe the tool you want and Fuser builds it, with the controls you asked for.

Ways to use this tool

Adjust detection and extraction settings to inspect, count, and separate objects from a single image.

Count items in a product image

Upload an image with visually separate products or items to get an object count and a numbered detection preview.

Separate figures in a group image

Use Extraction View to inspect detected figures as isolated object images rather than only viewing the original image.

Review detected object locations

Use the labeled preview and JSON metadata to check each object ID and its bounding box coordinates.

Create isolated object images

Generate extracted images with the background removed and crops fitted to each object’s non-transparent bounds.

Reduce text and watermark detections

Turn on Exclude text to avoid treating visible text or watermarks as detected objects.

Tune crowded-object detection

Adjust sensitivity, minimum size, nearby-object merging, padding, and the maximum object count for the image.

Frequently asked questions

Upload one image as the tool’s required input. The tool detects visually separate foreground objects or figures in that image.

It returns a preview image, an object count, JSON metadata, and extracted object images. The metadata includes an ID and bounding box coordinates for each detected object.

Preview mode switches between Original, Detection, and Extraction views. Sensitivity, minimum size, nearby-shape merging, text and watermark exclusion, padding, and maximum objects change how detection or extraction is handled.

You can try it on this page without an account. Downloading more than once or opening it in Fuser asks you to sign up.

Open the tool in Fuser and combine it with other nodes. Its preview, count, JSON metadata, and extracted image results can be used as outputs for the next steps in that workflow.